Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Nov 22, 2021
Date Accepted: Jan 31, 2022
Patient-level Fall Risk Prediction using the Observational Medical Outcomes Partnership’s Common Data Model: A pilot feasibility study
ABSTRACT
Background:
Falls in acute care settings threaten patients' safety. Researchers have been developing fall risk prediction models and exploring risk factors to provide evidence-based fall prevention practices. However, such efforts compromise insufficient samples, limited covariates, and a lack of standardized methodologies that aid study replication.
Objective:
The objectives of this study were to (1) convert fall-related EHR data into the standardized Observational Medical Outcome Partnership's (OMOP) Common Data Model (CDM) data format and (2) develop models that predict fall risk at two risk time periods: (a) within seven days of admission and (b) during entire hospital stays, using OMOP CDM data as a pilot feasibility test.
Methods:
We converted fall-related electronic health records data including nursing notes, fall risk assessment sheet, patient acuity assessment sheet, and clinical observation sheet,into standardized OMOP CDM data by the extraction, transformation and load process. Then, we developed fall risk prediction models in two different risk time periods using lasso logistic regression (LLR) and random forest algorithms.
Results:
In total, 6,277 nursing statements, 747,049,486 clinical observation sheet records, 1,554,775 fall-risk scores, and 5,685,011 patient acuity scores were converted into OMOP CDM format. The models achieved an area under the receiver operating characteristic curve of 0.692–0.726, higher than for the Hendrich II Fall Risk ModelTM. Moreover, patient acuity score, falls history, age ≥60, and movement disorder, and central nervous system agents were the most significant predictors in the LLR models.
Conclusions:
To enhance the models’ performance further, we are currently converting all nursing notes records into the OMOP CDM data format, which will then be included in the models. Thus, in the near future, the performance of fall risk prediction models could be improved through the application of abundant nursing records and external validation.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.